My hunch would be that the results from the talk wouldn't materially change, except that the Mutex numbers would perhaps be _slightly_ better. The scalability issue would remain though, as it is fundamental to mutexes!

Can you link to the discussion this is referencing? I can't imagine parking_lot outright replacing the mutex in std, rather than being added as an optional alternative... what would be the supported way of deliberately using the platform-native mutex?

parking-lot mutexes don't support lock poisoning like the standard library mutexes. Wouldn't this be a totally breaking change? Unless poisoning has been added to parking-lot?